Share：
Share this content in WeChat
X
[Chinese][PDF]2431
• Review •
Advances in radiomics and deep learning in predicting colorectal cancer-related gene mutations
ZHOU Boqi  CAO Yuntai  YANG Airu  HOU Yuyin  CAO Mingtai 

Cite this article as: ZHOU B Q, CAO Y T, YANG A R, et al. Advances in radiomics and deep learning in predicting colorectal cancer-related gene mutations[J]. Chin J Magn Reson Imaging, 2025, 16(2): 198-203. DOI:10.12015/issn.1674-8034.2025.02.032.


[Abstract] Colorectal cancer is a prevalent malignant tumor of the digestive tract, characterized by a high mortality rate. In recent years, precision treatment models for colorectal cancer based on molecular markers have emerged as significant advancements in disease management. In this context, rat sarcoma (RAS) and v-raf murine sarcoma viral oncogene homolog B1 (BRAF) genes serve as critical indicators for the molecular subtyping of colorectal cancer, playing an essential role in developing treatment strategies, assessing tumor prognosis, and predicting recurrence risk. Currently, pathological biopsy remains the gold standard for diagnosing genetic mutations in colorectal cancer patients; however, its invasive nature and limited reproducibility hinder its application in clinical decision-making processes. Given this situation, there is an urgent need to develop non-invasive and precise methods for detecting genetic mutations in colorectal cancer patients to provide more effective support for clinical decisions. This article aims to review the advancements in imaging genomics and deep learning concerning predicting gene mutations associated with colorectal cancer, offering new research perspectives and potential therapeutic strategies for the clinical diagnosis and management of these patients.
[Keywords] colorectal cancer；genetic mutation；magnetic resonance imaging；computed tomography；radiomics；deep learning

ZHOU Boqi   CAO Yuntai*   YANG Airu   HOU Yuyin   CAO Mingtai  

Image Center of Affiliated Hospital of Qinghai University, Xining 810001, China

Corresponding author: CAO Y T, E-mail: caoyt18@lzu.edu.cn

Conflicts of interest   None.

Received  2024-10-22
Accepted  2025-02-10
DOI: 10.12015/issn.1674-8034.2025.02.032
Cite this article as: ZHOU B Q, CAO Y T, YANG A R, et al. Advances in radiomics and deep learning in predicting colorectal cancer-related gene mutations[J]. Chin J Magn Reson Imaging, 2025, 16(2): 198-203. DOI:10.12015/issn.1674-8034.2025.02.032.

[1]
BRAY F, LAVERSANNE M, SUNG H, et al. Global cancer statistics 2022: GLOBOCAN estimates of incidence and mortality worldwide for 36 cancers in 185 countries[J]. CA Cancer J Clin, 2024, 74(3): 229-263. DOI: 10.3322/caac.21834.
[2]
ALBADARI N, XIE Y, LI W. Deciphering treatment resistance in metastatic colorectal cancer: roles of drug transports, EGFR mutations, and HGF/c-MET signaling[J/OL]. Front Pharmacol, 2023, 14: 1340401 [2025-02-10]. https://pubmed.ncbi.nlm.nih.gov/38269272/. DOI: 10.3389/fphar.2023.1340401.
[3]
DAKAL T C, BHUSHAN R, XU C M, et al. Intricate relationship between cancer stemness, metastasis, and drug resistance[J/OL]. MedComm, 2024, 5(10): e710 [2025-02-10]. https://pubmed.ncbi.nlm.nih.gov/39309691/. DOI: 10.1002/mco2.710.
[4]
JOHNSON D, CHEE C E, WONG W, et al. Current advances in targeted therapy for metastatic colorectal cancer - Clinical translation and future directions[J/OL]. Cancer Treat Rev, 2024, 125: 102700 [2025-02-10]. https://pubmed.ncbi.nlm.nih.gov/38422896/. DOI: 10.1016/j.ctrv.2024.102700.
[5]
SALVA DE TORRES C, BARAIBAR I, SAOUDI GONZÁLEZ N, et al. Current and emerging treatment paradigms in colorectal cancer: integrating hallmarks of cancer[J/OL]. Int J Mol Sci, 2024, 25(13): 6967 [2025-02-10]. https://pubmed.ncbi.nlm.nih.gov/39000083/. DOI: 10.3390/ijms25136967.
[6]
SONG Y L, CHEN M, WEI Y H, et al. Signaling pathways in colorectal cancer: implications for the target therapies[J/OL]. Mol Biomed, 2024, 5(1): 21 [2025-02-10]. https://pubmed.ncbi.nlm.nih.gov/38844562/. DOI: 10.1186/s43556-024-00178-y.
[7]
ZHANG K, REN Y Y, XU S F, et al. A clinical-radiomics model incorporating T2-weighted and diffusion-weighted magnetic resonance images predicts the existence of lymphovascular invasion/perineural invasion in patients with colorectal cancer[J]. Med Phys, 2021, 48(9): 4872-4882. DOI: 10.1002/mp.15001.
[8]
CHEN M T, JIANG Y D, ZHOU X H, et al. Dual-energy computed tomography in detecting and predicting lymph node metastasis in malignant tumor patients: A comprehensive review[J]. Diagnostics, 2024, 14(4): 377. DOI: 10.3390/diagnostics14040377.
[9]
GRANATA V, FUSCO R, SETOLA S V, et al. Machine learning and radiomics analysis by computed tomography in colorectal liver metastases patients for RAS mutational status prediction[J]. Radiol Med, 2024, 129(7): 957-966. DOI: 10.1007/s11547-024-01828-5.
[10]
LI S L, YUAN L, YUE M Y, et al. Early evaluation of liver metastasis using spectral CT to predict outcome in patients with colorectal cancer treated with FOLFOXIRI and bevacizumab[J/OL]. Cancer Imaging, 2023, 23(1): 30 [2025-02-10]. https://pubmed.ncbi.nlm.nih.gov/36964617/. DOI: 10.1186/s40644-023-00547-w.
[11]
MILAN N, NAVARRIA F, CECCHIN E, et al. Somatic pharmacogenomics in the treatment prognosis of locally advanced rectal cancer patients: a narrative review of the literature[J]. Expert Rev Clin Pharmacol, 2024, 17(8): 683-719. DOI: 10.1080/17512433.2024.2375449.
[12]
GROTHEY A, FAKIH M, TABERNERO J. Management of BRAF-mutant metastatic colorectal cancer: a review of treatment options and evidence-based guidelines[J]. Ann Oncol, 2021, 32(8): 959-967. DOI: 10.1016/j.annonc.2021.03.206.
[13]
CHATILA W K, KIM J K, WALCH H, et al. Genomic and transcriptomic determinants of response to neoadjuvant therapy in rectal cancer[J]. Nat Med, 2022, 28(8): 1646-1655. DOI: 10.1038/s41591-022-01930-z.
[14]
YIN Z P, LI H, ZHAO H, et al. CircRAPGEF5 acts as a modulator of RAS/RAF/MEK/ERK signaling during colorectal carcinogenesis[J/OL]. Heliyon, 2024, 10(16): e36133 [2025-02-10]. https://pubmed.ncbi.nlm.nih.gov/39229520/. DOI: 10.1016/j.heliyon.2024.e36133.
[15]
ESCHER T E, SATCHELL K J F. RAS degraders: The new frontier for RAS-driven cancers[J]. Mol Ther, 2023, 31(7): 1904-1919. DOI: 10.1016/j.ymthe.2023.03.017.
[16]
GARCÍA-ESPAÑA A, PHILIPS M R. Origin and evolution of RAS membrane targeting[J]. Oncogene, 2023, 42(21): 1741-1750. DOI: 10.1038/s41388-023-02672-z.
[17]
FENG J J, HU Z W, XIA X T, et al. Feedback activation of EGFR/wild-type RAS signaling axis limits KRASG12D inhibitor efficacy in KRASG12D-mutated colorectal cancer[J]. Oncogene, 2023, 42(20): 1620-1633. DOI: 10.1038/s41388-023-02676-9.
[18]
MOZZARELLI A M, SIMANSHU D K, CASTEL P. Functional and structural insights into RAS effector proteins[J]. Mol Cell, 2024, 84(15): 2807-2821. DOI: 10.1016/j.molcel.2024.06.027.
[19]
TSAI H L, LIN C C, SUNG Y C, et al. The emergence of RAS mutations in patients with RAS wild-type mCRC receiving cetuximab as first-line treatment: a noninterventional, uncontrolled multicenter study[J]. Br J Cancer, 2023, 129(6): 947-955. DOI: 10.1038/s41416-023-02366-z.
[20]
BENSON A B, VENOOK A P, ADAM M, et al. Colon cancer, version 3.2024, NCCN clinical practice guidelines in oncology[J/OL]. J Natl Compr Canc Netw, 2024, 22(2 D): e240029 [2025-02-10]. https://pubmed.ncbi.nlm.nih.gov/38862008/. DOI: 10.6004/jnccn.2024.0029.
[21]
MARTINELLI E, ARNOLD D, CERVANTES A, et al. European expert panel consensus on the clinical management of BRAFV600E-mutant metastatic colorectal cancer[J/OL]. Cancer Treat Rev, 2023, 115: 102541 [2025-02-10]. https://pubmed.ncbi.nlm.nih.gov/36931147/. DOI: 10.1016/j.ctrv.2023.102541.
[22]
ZHAO J, JIANG S, LIAO X, et al. Analysis of the relationship between KRAS NRAS BRAF HER2 gene mutations and MSI status and clinical features in colorectal cancer patients[J]. Int J Lab Med, 2024, 45(19): 2360-2365, 2371. DOI: 10.3969/j.issn.1673-4130.2024.19.011.
[23]
VARGAS A, SAADEH M, RICHARD BOLAND C, et al. Genetic testing in colorectal cancer: towards a better understanding and utilization by clinicians[J]. J Clin Gastroenterol, 2024, 58(10): 945-949. DOI: 10.1097/MCG.0000000000002047.
[24]
PENG J J, HUANG D, POSTON G, et al. The molecular heterogeneity of sporadic colorectal cancer with different tumor sites in Chinese patients[J]. Oncotarget, 2017, 8(30): 49076-49083. DOI: 10.18632/oncotarget.16176.
[25]
WANG F H, ZHANG X T, TANG L, et al. The Chinese society of clinical oncology (CSCO): clinical guidelines for the diagnosis and treatment of gastric cancer, 2023[J]. Cancer Commun, 2024, 44(1): 127-172. DOI: 10.1002/cac2.12516.
[26]
RASOOL M, HAQUE A, ALHARTHI M, et al. The mutational spectrum of NRAS gene discovers a novel frameshift mutation (E49R) in Saudi colorectal cancer patients[J/OL]. Cancer Cell Int, 2025, 25(1): 21 [2025-02-10]. https://pubmed.ncbi.nlm.nih.gov/39844204/. DOI: 10.1186/s12935-025-03652-x.
[27]
INCHINGOLO R, MAINO C, CANNELLA R, et al. Radiomics in colorectal cancer patients[J]. World J Gastroenterol, 2023, 29(19): 2888-2904. DOI: 10.3748/wjg.v29.i19.2888.
[28]
HUANG E P, O'CONNOR J P B, MCSHANE L M, et al. Criteria for the translation of radiomics into clinically useful tests[J]. Nat Rev Clin Oncol, 2023, 20(2): 69-82. DOI: 10.1038/s41571-022-00707-0.
[29]
D'ANTONOLI T A, CAVALLO A U, VERNUCCIO F, et al. Reproducibility of radiomics quality score: an intra- and inter-rater reliability study[J]. Eur Radiol, 2024, 34(4): 2791-2804. DOI: 10.1007/s00330-023-10217-x.
[30]
YANG L, DONG D, FANG M J, et al. Can CT-based radiomics signature predict KRAS/NRAS/BRAF mutations in colorectal cancer?[J]. Eur Radiol, 2018, 28(5): 2058-2067. DOI: 10.1007/s00330-017-5146-8.
[31]
LIN L B, CHEN X L, XU H, et al. CT-based radiomic model for predicting KRAS gene mutation status in colorectal cancer[J]. Chin J Med Imag, 2023, 31(6): 617-621, 629. DOI: 10.3969/j.issn.1005-5185.2023.06.012.
[32]
HU J F, XIA X Y, WANG P, et al. Predicting Kirsten rat sarcoma virus gene mutation status in patients with colorectal cancer by radiomics models based on Multiphasic CT[J/OL]. Front Oncol, 2022, 12: 848798 [2025-02-10]. https://pubmed.ncbi.nlm.nih.gov/35814386/. DOI: 10.3389/fonc.2022.848798.
[33]
ZHAO H Y, SU Y X, WANG Y, et al. Using tumor habitat-derived radiomic analysis during pretreatment 18F-FDG PET for predicting KRAS/NRAS/BRAF mutations in colorectal cancer[J/OL]. Cancer Imaging, 2024, 24(1): 26 [2025-02-10]. https://pubmed.ncbi.nlm.nih.gov/38342905/. DOI: 10.1186/s40644-024-00670-2.
[34]
TANG X, HUANG H L, DU P, et al. Intratumoral and peritumoral CT-based radiomics strategy reveals distinct subtypes of non-small-cell lung cancer[J]. J Cancer Res Clin Oncol, 2022, 148(9): 2247-2260. DOI: 10.1007/s00432-022-04015-z.
[35]
LI M M, XU G D, ZHOU H, et al. Computed tomography-based radiomics nomogram for the pre-operative prediction of BRAF mutation and clinical outcomes in patients with colorectal cancer: a double-center study[J/OL]. 2023, 96(1148): 20230019 [2025-02-10]. https://pubmed.ncbi.nlm.nih.gov/37195006/. DOI: 10.1259/bjr.20230019.
[36]
XUE T, PENG H, CHEN Q L, et al. Preoperative prediction of BRAF mutation status in colorectal cancer using a clinical-radiomics model[J]. Acad Radiol, 2022, 29(9): 1298-1307. DOI: 10.1016/j.acra.2021.12.016.
[37]
URBANIEC-STOMPÓR J, MICHALAK M, GODLEWSKI J. Correlating ultrastructural changes in the invasion area of colorectal cancer with CT and MRI imaging[J/OL]. Int J Mol Sci, 2024, 25(18): 9905 [2025-02-10]. https://pubmed.ncbi.nlm.nih.gov/39337393/. DOI: 10.3390/ijms25189905.
[38]
CUI Y F, LIU H H, REN J L, et al. Development and validation of a MRI-based radiomics signature for prediction of KRAS mutation in rectal cancer[J]. Eur Radiol, 2020, 30(4): 1948-1958. DOI: 10.1007/s00330-019-06572-3.
[39]
ZHANG Z Y, SHEN L J, WANG Y, et al. MRI radiomics signature as a potential biomarker for predicting KRAS status in locally advanced rectal cancer patients[J/OL]. Front Oncol, 2021, 11: 614052 [2025-02-10]. https://pubmed.ncbi.nlm.nih.gov/34026605/. DOI: 10.3389/fonc.2021.614052.
[40]
ALSHUHRI M S, ALDUHYYIM A, AL-MUBARAK H, et al. Investigating the feasibility of predicting KRAS status, tumor staging, and extramural venous invasion in colorectal cancer using inter-platform magnetic resonance imaging radiomic features[J/OL]. Diagnostics, 2023, 13(23): 3541 [2025-02-10]. https://pubmed.ncbi.nlm.nih.gov/38066782/. DOI: 10.3390/diagnostics13233541.
[41]
XU Y, XU Q, MA Y, et al. Characterizing MRI features of rectal cancers with different KRAS status[J/OL]. BMC Cancer, 2019, 19(1): 1111 [2025-02-10]. https://pubmed.ncbi.nlm.nih.gov/31727020/. DOI: 10.1186/s12885-019-6341-6.
[42]
JIANG X, HU Z, WANG S, et al. Deep learning for medical image-based cancer diagnosis[J/OL]. Cancers (Basel), 2023, 15(14): 3608 [2025-02-10]. https://pubmed.ncbi.nlm.nih.gov/37509272/. DOI: 10.3390/cancers15143608.
[43]
YUE T, WANG Y, ZHANG L, et al. Deep learning for genomics: from early neural nets to modern large language models[J/OL]. Int J Mol Sci, 2023, 24(21): 15858 [2025-02-10]. https://pubmed.ncbi.nlm.nih.gov/37958843/. DOI: 10.3390/ijms242115858.
[44]
NASSER M, YUSOF U K. Deep learning based methods for breast cancer diagnosis: a systematic review and future direction[J/OL]. Diagnostics (Basel), 2023, 13(1): 161 [2025-02-10]. https://pubmed.ncbi.nlm.nih.gov/36611453/. DOI: 10.3390/diagnostics13010161.
[45]
LIU H H, YIN H K, LI J N, et al. A deep learning model based on MRI and clinical factors facilitates noninvasive evaluation of KRAS mutation in rectal cancer[J]. J Magn Reson Imaging, 2022, 56(6): 1659-1668. DOI: 10.1002/jmri.28237.
[46]
HE K, LIU X, LI M, et al. Noninvasive KRAS mutation estimation in colorectal cancer using a deep learning method based on CT imaging[J/OL]. BMC Med Imaging, 2020, 20(1): 59 [2025-02-10]. https://pubmed.ncbi.nlm.nih.gov/32487083/. DOI: 10.1186/s12880-020-00457-4.
[47]
LI X J, CHI X D, HUANG P J, et al. Deep neural network for the prediction of KRAS, NRAS, and BRAF genotypes in left-sided colorectal cancer based on histopathologic images[J/OL]. Comput Med Imaging Graph, 2024, 115: 102384 [2025-02-10]. https://pubmed.ncbi.nlm.nih.gov/38759471/. DOI: 10.1016/j.compmedimag.2024.102384.
[48]
MA Y L, GUO Y Z, CUI W G, et al. SG-Transunet: a segmentation-guided Transformer U-Net model for KRAS gene mutation status identification in colorectal cancer[J/OL]. Comput Biol Med, 2024, 173: 108293 [2025-02-10]. https://pubmed.ncbi.nlm.nih.gov/38574528/. DOI: 10.1016/j.compbiomed.2024.108293.
[49]
CAI M L, ZHAO L, QIANG Y, et al. CHNet: a multi-task global-local Collaborative Hybrid Network for KRAS mutation status prediction in colorectal cancer[J/OL]. Artif Intell Med, 2024, 155: 102931 [2025-02-10]. https://pubmed.ncbi.nlm.nih.gov/39094228/. DOI: 10.1016/j.artmed.2024.102931.
[50]
LV Z L, YAN R, LIN Y X, et al. A disentangled representation-based multimodal fusion framework integrating pathomics and radiomics for KRAS mutation detection in colorectal cancer[J]. Big Data Min Anal, 2024, 7(3): 590-602. DOI: 10.26599/BDMA.2024.9020012.
[51]
BERA K, BRAMAN N, GUPTA A, et al. Predicting cancer outcomes with radiomics and artificial intelligence in radiology[J]. Nat Rev Clin Oncol, 2022, 19(2): 132-146. DOI: 10.1038/s41571-021-00560-7.
[52]
UNGER M, KATHER J N. Deep learning in cancer genomics and histopathology[J/OL]. Genome Med, 2024, 16(1): 44 [2025-02-10]. https://pubmed.ncbi.nlm.nih.gov/38539231/. DOI: 10.1186/s13073-024-01315-6.
[53]
LIU Y, WEI X Q, FENG X, et al. Repeatability of radiomics studies in colorectal cancer: a systematic review[J/OL]. BMC Gastroenterol, 2023, 23(1): 125 [2025-02-10]. https://pubmed.ncbi.nlm.nih.gov/37059990/. DOI: 10.1186/s12876-023-02743-1.

PREV Research progress on artificial intelligence in MRI for breast cancer diagnosis and treatment response prediction
NEXT The research progress of MRI in predicting the efficacy of neoadjuvant chemoradiotherapy for rectal cancer
  


LINK


Tel & Fax: +8610-67113815    E-mail: editor@cjmri.cn